Single Cell Biological Microlasers Powered by Deep Learning

Cellular lasers are cutting-edge technologies for biomedical applications. Due to the enhanced interactions between light and cells in microcavities, cellular properties and subtle changes of cells can be significantly reflected by the laser emission characteristics. In particular, transverse laser modes from single-cell lasers which utilize Fabry-Perot cavities are highly correlated to the spatial biophysical properties of cells. However, the high chaotic and complex variation of laser modes limits their practical applications for cell detections. Deep learning technique has demonstrated its powerful capability in solving complex imaging problems, which is expected to be applied for cell detections based on laser mode imaging. In this study, deep learning technique was applied to analyze laser modes generated from single-cell lasers, in which a correlation between laser modes and physical properties of cells was built. As a proof-of-concept, we demonstrated the predictions of cell sizes using deep learning based on laser mode imaging. In the first part, bioinspired cell models were fabricated to systematically study how cell sizes affect the characteristics of laser modes. By training a convolutional neuron network (CNN) model with laser mode images, predictions of cell model diameters with a sub-wavelength accuracy were achieved. In the second part, deep learning was employed to study laser modes generated from biological cells. By training a CNN model with laser mode images acquired from astrocyte cells, predictions of cell sizes with a sub-wavelength accuracy were also achieved. The results show the great potential of laser mode imaging integrated with deep learning for cell analysis and biophysical studies.